Reinforcement Learning on Seeker
18.6Episode ReturnGenerator Mask
Evaluation results
| Method | Links | |
|---|---|---|
| Generator MaskMasking Strategy=Generator Masking2024.06 | 18.6 | |
| Distributional MaskMasking Strategy=Distributional Masking2024.06 | -13.66 | |
| Ray MaskMasking Strategy=Ray Masking2024.06 | -20.45 | |
| ReplacementMasking Strategy=Action Replacement2024.06 | -60.21 | |
| BaselineMasking Strategy=None2024.06 | -71.03 |